Solutions Applied Data Scientist

Responsibilities

• Design, construct, and validate complex healthcare data cohorts used for AI model training
• Translate research requirements and customer needs into practical dataset definitions and SQL logic
• Act as a technical partner to Solutions Leads to solve complex data challenges, including multi-source joins and dataset linkage
• Perform data completeness analysis, investigate anomalies, and verify cohort logic results
• Evaluate the feasibility of requested variables and labels against available real-world data sources
• Collaborate with delivery engineers to implement necessary changes to data pipelines and infrastructure
• Develop reusable SQL templates, automated validation checks, and scripts to improve delivery workflows

Requirements

• Experience working with large, structured healthcare datasets
• Strong SQL and Python skills, including experience writing complex queries and data transformations
• Experience using Claude Code or Codex
• Experience with data validation, exploratory analysis, and performing completeness checks
• Proficiency with structured file formats such as CSV and Parquet
• Ability to translate ambiguous research requirements into concrete, actionable data logic
• Strong communication skills for collaborating with both technical and non-technical stakeholders

About the Company

Protege is building a platform to solve AI's biggest unmet need: access to high-quality training data. We facilitate the secure, efficient, and privacy-centric exchange of AI training data, helping ambitious teams power their models with the right information. We are a lean, fast-moving, high-trust team of builders obsessed with velocity and impact.